Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2653 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.6388. Min Act: -0.0000

Data Index: 333458 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.5147. Min Act: -0.0000

Data Index: 269906 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.0747. Min Act: -0.0000

Data Index: 437017 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.0244. Min Act: -0.0000

Data Index: 185516 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.0207. Min Act: -0.0000

Data Index: 361176 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.9850. Min Act: -0.0000

Data Index: 226898 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.8771. Min Act: -0.0000

Data Index: 23635 (C4 (Web Text))

Max Activating Token Index: 765

Text #7

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.8396. Min Act: -0.0000

Data Index: 1063047 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.8340. Min Act: -0.0000

Data Index: 943183 (C4 (Web Text))

Max Activating Token Index: 781

Text #9

Max Range: 2.6388. Min Range: -2.6388

Max Act: 2.0168. Min Act: -0.0000

Data Index: 720598 (C4 (Web Text))

Max Activating Token Index: 240

Text #10

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.9008. Min Act: -0.0000

Data Index: 1195647 (C4 (Web Text))

Max Activating Token Index: 531

Text #11

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.8690. Min Act: -0.0000

Data Index: 1254310 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.7947. Min Act: -0.0000

Data Index: 457995 (C4 (Web Text))

Max Activating Token Index: 388

Text #13

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.7860. Min Act: -0.0000

Data Index: 5527 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.7414. Min Act: -0.0000

Data Index: 39625 (C4 (Web Text))

Max Activating Token Index: 126

Text #15

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.5582. Min Act: -0.0000

Data Index: 1375470 (Python Code)

Max Activating Token Index: 178

Text #16

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.5291. Min Act: -0.0000

Data Index: 440668 (C4 (Web Text))

Max Activating Token Index: 28

Text #17

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.5902. Min Act: -0.0000

Data Index: 665162 (C4 (Web Text))

Max Activating Token Index: 188

Text #18

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.3903. Min Act: -0.0000

Data Index: 775717 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 2.6388. Min Range: -2.6388

Max Act: 1.4700. Min Act: -0.0000

Data Index: 1594672 (Python Code)

Max Activating Token Index: 243